Instructions to use ariel-pillar/phi-4_function_calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ariel-pillar/phi-4_function_calling with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ariel-pillar/phi-4_function_calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ariel-pillar/phi-4_function_calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ariel-pillar/phi-4_function_calling:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ariel-pillar/phi-4_function_calling:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Use Docker

docker model run hf.co/ariel-pillar/phi-4_function_calling:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use ariel-pillar/phi-4_function_calling with Ollama:
```
ollama run hf.co/ariel-pillar/phi-4_function_calling:Q4_K_M
```
Unsloth Desktop

How to use ariel-pillar/phi-4_function_calling with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ariel-pillar/phi-4_function_calling:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ariel-pillar/phi-4_function_calling with Docker Model Runner:
```
docker model run hf.co/ariel-pillar/phi-4_function_calling:Q4_K_M
```

Lemonade

How to use ariel-pillar/phi-4_function_calling with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ariel-pillar/phi-4_function_calling:Q4_K_M

Run and chat with the model

lemonade run user.phi-4_function_calling-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ariel-pillar/phi-4_function_calling with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ariel-pillar/phi-4_function_calling:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ariel-pillar/phi-4_function_calling with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ariel-pillar/phi-4_function_calling:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ariel-pillar/phi-4_function_calling:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ariel-pillar commited on May 31, 2025

Commit

e29b963

verified ·

1 Parent(s): 8ae50d9

make clear that readme is about tool use

Browse files

Files changed (1) hide show

README.md +39 -9

README.md CHANGED Viewed

@@ -1,10 +1,18 @@
----
-base_model:
-- microsoft/Phi-4-mini-instruct
----
-# Phi-4-mini-instruct with llama-server
-This repository contains instructions for running the Phi-4-mini-instruct model using llama-server, which provides a ChatGPT-compatible API interface.
 ## Prerequisites
@@ -31,7 +39,6 @@ Start the llama-server with the following command:
 llama-server \
     --model models/Phi-4-mini-instruct-Q4_K_M-modified.gguf \
     --port 8082 \
-    --verbose \
     --jinja
 ```
@@ -71,6 +78,27 @@ curl http://localhost:8082/v1/chat/completions \
   }'
 ```
 ## API Endpoints
 The server provides a ChatGPT-compatible API with the following main endpoints:
@@ -82,8 +110,10 @@ The server provides a ChatGPT-compatible API with the following main endpoints:
 ## Notes
 - The server uses the same API format as OpenAI's ChatGPT API, making it compatible with many existing tools and libraries
-- The `--jinja` flag enables proper chat template formatting for the model
 - The model name in the requests can be set to "any-model" as shown in the examples
 ## Troubleshooting
@@ -96,4 +126,4 @@ If you encounter issues:
 ## License
-Please ensure you comply with the model's license terms when using it.

+---
+base_model:
+- microsoft/Phi-4-mini-instruct
+---
+# Phi-4-mini-instruct with llama-server (Tool-Enhanced Version)
+This repository contains instructions for running a modified version of the Phi-4-mini-instruct model using llama-server. This version has been enhanced to support tool usage, allowing the model to interact with external tools and APIs through a ChatGPT-compatible interface.
+## Model Capabilities
+This modified version of Phi-4-mini-instruct includes:
+- Full support for tool usage and function calling
+- Custom chat template optimized for tool interactions
+- Ability to process and respond to tool outputs
+- ChatGPT-compatible API interface
 ## Prerequisites
 llama-server \
     --model models/Phi-4-mini-instruct-Q4_K_M-modified.gguf \
     --port 8082 \
     --jinja
 ```
   }'
 ```
+### Example 3: Using Tools
+```bash
+curl http://localhost:8082/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "any-model",
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful AI assistant that can use tools.",
+        "tools": "[{\"name\": \"calculator\", \"description\": \"Useful for performing mathematical calculations\", \"parameters\": {\"type\": \"object\", \"properties\": {\"expression\": {\"type\": \"string\", \"description\": \"The mathematical expression to evaluate\"}}}}]"
+      },
+      {
+        "role": "user",
+        "content": "What is 235 * 89?"
+      }
+    ]
+  }'
+```
 ## API Endpoints
 The server provides a ChatGPT-compatible API with the following main endpoints:
 ## Notes
 - The server uses the same API format as OpenAI's ChatGPT API, making it compatible with many existing tools and libraries
+- The `--jinja` flag enables proper chat template formatting for the model, which is essential for tool usage
 - The model name in the requests can be set to "any-model" as shown in the examples
+- This version supports system messages with tool definitions
+- Tool responses are properly handled through the chat template
 ## Troubleshooting
 ## License
+Please ensure you comply with the model's license terms when using it.